# Re-envisioning Euclid Galaxy Morphology: Identifying and Interpreting Features with Sparse Autoencoders

arXiv: https://arxiv.org/abs/2510.23749 · HTML: https://mlsanity.com/paper/2510.23749/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 19 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Builds on (most cited first, 14 of 14)

- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning](https://mlsanity.com/paper/2212.14532/) (2022)
- [k-Sparse Autoencoders](https://mlsanity.com/paper/1312.5663/) (2013)
- [A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders](https://mlsanity.com/paper/2409.14507/) (2024)
- [Learning Multi-Level Features with Matryoshka Sparse Autoencoders](https://mlsanity.com/paper/2503.17547/) (2025)
- [SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability](https://mlsanity.com/paper/2503.09532/) (2025)
- [Do Self-Supervised and Supervised Methods Learn Similar Visual Representations?](https://mlsanity.com/paper/2110.00528/) (2021)
- [Disentangling Dense Embeddings with Sparse Autoencoders](https://mlsanity.com/paper/2408.00657/) (2024)
- [Position: Use Sparse Autoencoders to Discover Unknowns](https://mlsanity.com/paper/2506.23845/) (2025)
- [Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models](https://mlsanity.com/paper/2411.00743/) (2024)
- [AstroMAE: Redshift Prediction Using a Masked Autoencoder with a Novel Fine-Tuning Architecture](https://mlsanity.com/paper/2409.01825/) (2024)
- [Insights on Galaxy Evolution from Interpretable Sparse Feature Networks](https://mlsanity.com/paper/2501.00089/) (2024)

## Built on by (most cited first, 2 of 2)

- [Weak-to-Strong Generalization via Direct On-Policy Distillation](https://mlsanity.com/paper/2607.05394/) (2026)
- [A survey detection channel overrides the pixels in an astronomical foundation model, and biases tomographic mean redshifts](https://mlsanity.com/paper/2608.23626/) (2026)

## Abstract (arXiv)

Sparse Autoencoders (SAEs) can efficiently identify candidate monosemantic features from pretrained neural networks for galaxy morphology. We demonstrate this on Euclid Q1 images using both supervised (Zoobot) and new self-supervised (MAE) models. Our publicly released MAE achieves superhuman image reconstruction performance. While a Principal Component Analysis (PCA) on the supervised model primarily identifies features already aligned with the Galaxy Zoo decision tree, SAEs can identify interpretable features outside of this framework. SAE features also show stronger alignment than PCA with Galaxy Zoo labels. Although challenges in interpretability remain, SAEs provide a powerful engine for discovering astrophysical phenomena beyond the confines of human-defined classification.